# coding=utf-8 # Copyright 2018 The Google AI Language Team Authors and The HuggingFace Inc. team. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. # You may obtain a copy of the License at # # http://www.apache.org/licenses/LICENSE-2.0 # # Unless required by applicable law or agreed to in writing, software # distributed under the License is distributed on an "AS IS" BASIS, # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. """Tokenization classes.""" from __future__ import absolute_import, division, print_function, unicode_literals from __future__ import (absolute_import, division, print_function, unicode_literals) import collections import regex as re import json import sys import logging import os import unicodedata from io import open from .file_utils import cached_path logger = logging.getLogger(__name__) def whitespace_tokenize(text): """Runs basic whitespace cleaning and splitting on a piece of text.""" text = text.strip() if not text: return [] tokens = text.split() return tokens try: from functools import lru_cache except ImportError: # Just a dummy decorator to get the checks to run on python2 # because honestly I don't want to support a byte-level unicode BPE tokenizer on python 2 right now. def lru_cache(): return lambda func: func logger = logging.getLogger(__name__) PRETRAINED_VOCAB_ARCHIVE_MAP = {'gpt2': "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-vocab.json",} PRETRAINED_MERGES_ARCHIVE_MAP = {'gpt2': "https://s3.amazonaws.com/models.huggingface.co/bert/gpt2-merges.txt",} PRETRAINED_VOCAB_POSITIONAL_EMBEDDINGS_SIZE_MAP = {'gpt2': 1024,} VOCAB_NAME = 'vocab.json' MERGES_NAME = 'merges.txt' SPECIAL_TOKENS_NAME = 'special_tokens.txt' @lru_cache() def get_pairs(word): """Return set of symbol pairs in a word. Word is represented as tuple of symbols (symbols being variable-length strings). """ pairs = set() prev_char = word[0] for char in word[1:]: pairs.add((prev_char, char)) prev_char = char return pairs class GPT2Tokenizer(object): """ GPT-2 BPE tokenizer. Peculiarities: - Byte-level BPE """ @classmethod def from_pretrained(cls, pretrained_model_name_or_path='gpt2', cache_dir=None, *inputs, **kwargs): """ Download and cache the pre-trained model file if needed. """ if pretrained_model_name_or_path in PRETRAINED_VOCAB_ARCHIVE_MAP: vocab_file = PRETRAINED_VOCAB_ARCHIVE_MAP[pretrained_model_name_or_path] merges_file = PRETRAINED_MERGES_ARCHIVE_MAP[pretrained_model_name_or_path] special_tokens_file = None else: vocab_file = os.path.join(pretrained_model_name_or_path, VOCAB_NAME) merges_file = os.path.join(pretrained_model_name_or_path, MERGES_NAME) special_tokens_file = os.path.join(pretrained_model_name_or_path, SPECIAL_TOKENS_NAME) if not os.path.exists(special_tokens_file): special_tokens_file = None else: logger.info("loading special tokens file {}".format(special_tokens_file)) # redirect to the cache, if necessary try: resolved_vocab_file = cached_path(vocab_file, cache_dir=cache_dir) resolved_merges_file = cached_path(merges_file, cache_dir=cache_dir) except EnvironmentError: logger.error( "Model name '{}' was not found in model name list ({}). " "We assumed '{}' was a path or url but couldn't find files {} and {} " "at this path or url.".format( pretrained_model_name_or_path, ', '.join(PRETRAINED_VOCAB_ARCHIVE_MAP.keys()), pretrained_model_name_or_path, vocab_file, merges_file)) return None if resolved_vocab_file == vocab_file and resolved_merges_file == merges_file: logger.info("loading vocabulary file {}".format(vocab_file)) logger.info("loading merges file {}".format(merges_file)) else: logger.info("loading vocabulary file {} from cache at {}".format( vocab_file, resolved_vocab_file)) logger.info("loading merges file {} from cache at {}".format( merges_file, resolved_merges_file)) if pretrained_model_name_or_path in PRETRAINED_VOCAB_POSITIONAL_EMBEDDINGS_SIZE_MAP: # if we're using a pretrained model, ensure the tokenizer wont index sequences longer # than the number of positional embeddings max_len = PRETRAINED_VOCAB_POSITIONAL_EMBEDDINGS_SIZE_MAP[pretrained_model_name_or_path] kwargs['max_len'] = min(kwargs.get('max_len', int(1e12)), max_len) # Instantiate tokenizer. if special_tokens_file and 'special_tokens' not in kwargs: special_tokens = open(special_tokens_file, encoding='utf-8').read().split('\n')[:-1] else: special_tokens = kwargs.pop('special_tokens', []) tokenizer = cls(resolved_vocab_file, resolved_merges_file, special_tokens=special_tokens, *inputs, **kwargs) return tokenizer def __init__(self, vocab_file, merges_file, errors='replace', special_tokens=None, max_len=None): self.max_len = max_len if max_len is not None else int(1e12) self.encoder = json.load(open(vocab_file)) self.decoder = {v: k for k, v in self.encoder.items()} self.errors = errors # how to handle errors in decoding bpe_data = open(merges_file, encoding='utf-8').read().split('\n')[1:-1] bpe_merges = [tuple(merge.split()) for merge in bpe_data] self.bpe_ranks = dict(zip(bpe_merges, range(len(bpe_merges)))) self.cache = {} # Should haved added re.IGNORECASE so BPE merges can happen for capitalized versions of contractions self.pat = re.compile(r"""'s|'t|'re|'ve|'m|'ll|'d| ?\p{L}+| ?\p{N}+| ?[^\s\p{L}\p{N}]+|\s+(?!\S)|\s+""") self.special_tokens = {} self.special_tokens_decoder = {} self.set_special_tokens(special_tokens) def __len__(self): return len(self.encoder) + len(self.special_tokens) def set_special_tokens(self, special_tokens): """ Add a list of additional tokens to the encoder. The additional tokens are indexed starting from the last index of the current vocabulary in the order of the `special_tokens` list. """ if not special_tokens: self.special_tokens = {} self.special_tokens_decoder = {} return self.special_tokens = dict((tok, len(self.encoder) + i) for i, tok in enumerate(special_tokens)) self.special_tokens_decoder = {v: k for k, v in self.special_tokens.items()} logger.info("Special tokens {}".format(self.special_tokens)) def bpe(self, token): if token in self.cache: return self.cache[token] word = tuple(token) pairs = get_pairs(word) if not pairs: return token while True: bigram = min(pairs, key=lambda pair: self.bpe_ranks.get(pair, float('inf'))) if bigram not in self.bpe_ranks: break first, second = bigram new_word = [] i = 0 while i < len(word): try: j = word.index(first, i) new_word.extend(word[i:j]) i = j except: new_word.extend(word[i:]) break if word[i] == first and i < len(word) - 1 and word[i + 1] == second: new_word.append(first + second) i += 2 else: new_word.append(word[i]) i += 1 new_word = tuple(new_word) word = new_word if len(word) == 1: break else: pairs = get_pairs(word) word = ' '.join(word) self.cache[token] = word return word def tokenize(self, text): """ Tokenize a string. """ bpe_tokens = [] for token in re.findall(self.pat, text): bpe_tokens.extend(bpe_token for bpe_token in self.bpe(token).split(' ')) return bpe_tokens def convert_tokens_to_ids(self, tokens): """ Converts a sequence of tokens into ids using the vocab. """ ids = [] if isinstance(tokens, str) or (sys.version_info[0] == 2 and isinstance(tokens, unicode)): if tokens in self.special_tokens: return self.special_tokens[tokens] else: return self.encoder.get(tokens, 0) for token in tokens: if token in self.special_tokens: ids.append(self.special_tokens[token]) else: ids.append(self.encoder.get(token, 0)) if len(ids) > self.max_len: logger.warning( "Token indices sequence length is longer than the specified maximum " " sequence length for this OpenAI GPT model ({} > {}). Running this" " sequence through the model will result in indexing errors".format(len(ids), self.max_len) ) return ids def convert_ids_to_tokens(self, ids, skip_special_tokens=False): """Converts a sequence of ids in BPE tokens using the vocab.""" tokens = [] for i in ids: if i in self.special_tokens_decoder: if not skip_special_tokens: tokens.append(self.special_tokens_decoder[i]) else: tokens.append(self.decoder[i]) return tokens def encode(self, text): return self.convert_tokens_to_ids(self.tokenize(text)) def decode(self, tokens): text = ''.join([self.decoder[token] for token in tokens]) text = bytearray([self.byte_decoder[c] for c in text]).decode('utf-8', errors=self.errors) return text def save_vocabulary(self, vocab_path): """Save the tokenizer vocabulary and merge files to a directory.""" if not os.path.isdir(vocab_path): logger.error("Vocabulary path ({}) should be a directory".format(vocab_path)) return vocab_file = os.path.join(vocab_path, VOCAB_NAME) merge_file = os.path.join(vocab_path, MERGES_NAME) special_tokens_file = os.path.join(vocab_path, SPECIAL_TOKENS_NAME) with open(vocab_file, 'w', encoding='utf-8') as f: f.write(json.dumps(self.encoder, ensure_ascii=False)) index = 0 with open(merge_file, "w", encoding="utf-8") as writer: writer.write(u'#version: 0.2\n') for bpe_tokens, token_index in sorted(self.bpe_ranks.items(), key=lambda kv: kv[1]): if index != token_index: logger.warning("Saving vocabulary to {}: BPE merge indices are not consecutive." " Please check that the tokenizer is not corrupted!".format(merge_file)) index = token_index writer.write(' '.join(bpe_tokens) + u'\n') index += 1 index = len(self.encoder) with open(special_tokens_file, 'w', encoding='utf-8') as writer: for token, token_index in sorted(self.special_tokens.items(), key=lambda kv: kv[1]): if index != token_index: logger.warning("Saving special tokens vocabulary to {}: BPE indices are not consecutive." " Please check that the tokenizer is not corrupted!".format(special_tokens_file)) index = token_index writer.write(token + u'\n') index += 1 return vocab_file, merge_file, special_tokens_file class BasicTokenizer(object): """Runs basic tokenization (punctuation splitting, lower casing, etc.).""" def __init__(self, do_lower_case=True, never_split=("[UNK]", "[SEP]", "[PAD]", "[CLS]", "[MASK]")): """Constructs a BasicTokenizer. Args: do_lower_case: Whether to lower case the input. """ self.do_lower_case = do_lower_case self.never_split = never_split def tokenize(self, text): """Tokenizes a piece of text.""" text = self._clean_text(text) text = self._tokenize_chinese_chars(text) orig_tokens = whitespace_tokenize(text) split_tokens = [] for token in orig_tokens: if self.do_lower_case and token not in self.never_split: token = token.lower() token = self._run_strip_accents(token) split_tokens.extend(self._run_split_on_punc(token)) output_tokens = whitespace_tokenize(" ".join(split_tokens)) return output_tokens def _run_strip_accents(self, text): """Strips accents from a piece of text.""" text = unicodedata.normalize("NFD", text) output = [] for char in text: cat = unicodedata.category(char) if cat == "Mn": continue output.append(char) return "".join(output) def _run_split_on_punc(self, text): """Splits punctuation on a piece of text.""" if text in self.never_split: return [text] chars = list(text) i = 0 start_new_word = True output = [] while i < len(chars): char = chars[i] if _is_punctuation(char): output.append([char]) start_new_word = True else: if start_new_word: output.append([]) start_new_word = False output[-1].append(char) i += 1 return ["".join(x) for x in output] def _tokenize_chinese_chars(self, text): """Adds whitespace around any CJK character.""" output = [] for char in text: cp = ord(char) if self._is_chinese_char(cp): output.append(" ") output.append(char) output.append(" ") else: output.append(char) return "".join(output) def _is_chinese_char(self, cp): """Checks whether CP is the codepoint of a CJK character.""" if ((cp >= 0x4E00 and cp <= 0x9FFF) or # (cp >= 0x3400 and cp <= 0x4DBF) or # (cp >= 0x20000 and cp <= 0x2A6DF) or # (cp >= 0x2A700 and cp <= 0x2B73F) or # (cp >= 0x2B740 and cp <= 0x2B81F) or # (cp >= 0x2B820 and cp <= 0x2CEAF) or (cp >= 0xF900 and cp <= 0xFAFF) or # (cp >= 0x2F800 and cp <= 0x2FA1F)): # return True return False def _clean_text(self, text): """Performs invalid character removal and whitespace cleanup on text.""" output = [] for char in text: cp = ord(char) if cp == 0 or cp == 0xfffd or _is_control(char): continue if _is_whitespace(char): output.append(" ") else: output.append(char) return "".join(output) def _is_whitespace(char): """Checks whether `chars` is a whitespace character.""" # \t, \n, and \r are technically contorl characters but we treat them # as whitespace since they are generally considered as such. if char == " " or char == "\t" or char == "\n" or char == "\r": return True cat = unicodedata.category(char) if cat == "Zs": return True return False def _is_control(char): """Checks whether `chars` is a control character.""" # These are technically control characters but we count them as whitespace # characters. if char == "\t" or char == "\n" or char == "\r": return False cat = unicodedata.category(char) if cat.startswith("C"): return True return False def _is_punctuation(char): """Checks whether `chars` is a punctuation character.""" cp = ord(char) if ((cp >= 33 and cp <= 47) or (cp >= 58 and cp <= 64) or (cp >= 91 and cp <= 96) or (cp >= 123 and cp <= 126)): return True cat = unicodedata.category(char) if cat.startswith("P"): return True return False